2 papers
cs.AI2026
Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules
Cameron Pattison, Lorenzo Manuali, Seth Lazar
Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help evading rules imposed by an ill…
cs.CY2025
Can LLMs advance democratic values?
Seth Lazar, Lorenzo Manuali
LLMs are among the most advanced tools ever devised for understanding and generating natural language. Democratic deliberation and decision-making involve, at several distinct stag…